US8538239B2 - System and method for fingerprinting video - Google Patents

System and method for fingerprinting video Download PDF

Info

Publication number
US8538239B2
US8538239B2 US13/334,201 US201113334201A US8538239B2 US 8538239 B2 US8538239 B2 US 8538239B2 US 201113334201 A US201113334201 A US 201113334201A US 8538239 B2 US8538239 B2 US 8538239B2
Authority
US
United States
Prior art keywords
video
scene change
fingerprint
time interval
scene
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US13/334,201
Other languages
English (en)
Other versions
US20130163957A1 (en
Inventor
Ike Ikizyan
Marcus Kellerman
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Avago Technologies International Sales Pte Ltd
Original Assignee
Broadcom Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Broadcom Corp filed Critical Broadcom Corp
Priority to US13/334,201 priority Critical patent/US8538239B2/en
Assigned to BROADCOM CORPORATION reassignment BROADCOM CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: IKIZYAN, IKE, KELLERMAN, MARCUS
Priority to EP12005902.7A priority patent/EP2608107A3/en
Priority to TW101132784A priority patent/TWI551134B/zh
Priority to KR1020120105197A priority patent/KR20130079123A/ko
Priority to CN201210371363.7A priority patent/CN103198293B/zh
Publication of US20130163957A1 publication Critical patent/US20130163957A1/en
Priority to US13/968,616 priority patent/US9185338B2/en
Publication of US8538239B2 publication Critical patent/US8538239B2/en
Application granted granted Critical
Assigned to BANK OF AMERICA, N.A., AS COLLATERAL AGENT reassignment BANK OF AMERICA, N.A., AS COLLATERAL AGENT PATENT SECURITY AGREEMENT Assignors: BROADCOM CORPORATION
Assigned to AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD. reassignment AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: BROADCOM CORPORATION
Assigned to BROADCOM CORPORATION reassignment BROADCOM CORPORATION TERMINATION AND RELEASE OF SECURITY INTEREST IN PATENTS Assignors: BANK OF AMERICA, N.A., AS COLLATERAL AGENT
Assigned to AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITED reassignment AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITED MERGER (SEE DOCUMENT FOR DETAILS). Assignors: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.
Assigned to AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITED reassignment AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITED CORRECTIVE ASSIGNMENT TO CORRECT THE EFFECTIVE DATE OF THE MERGER PREVIOUSLY RECORDED AT REEL: 047230 FRAME: 0910. ASSIGNOR(S) HEREBY CONFIRMS THE MERGER. Assignors: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.
Assigned to AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITED reassignment AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITED CORRECTIVE ASSIGNMENT TO CORRECT THE ERROR IN RECORDING THE MERGER IN THE INCORRECT US PATENT NO. 8,876,094 PREVIOUSLY RECORDED ON REEL 047351 FRAME 0384. ASSIGNOR(S) HEREBY CONFIRMS THE MERGER. Assignors: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/91—Television signal processing therefor
    • H04N5/92—Transformation of the television signal for recording, e.g. modulation, frequency changing; Inverse transformation for playback
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G06V20/47—Detecting features for summarising video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes

Definitions

  • Video fingerprinting is useful for various purposes.
  • a video fingerprint refers to a way in which a video can be uniquely identified relative to other videos in a collection or corpus of many videos.
  • Video fingerprinting systems and methods in the art often lack robustness in the sense that they fail to identify clips, edited versions, and/or even full versions of a video that have been compressed or fail to comprise a bitwise match of a reference video.
  • Prior art video fingerprinting systems and methods may also fail to match a video under analysis to a reference video if the video quality has been degraded or otherwise altered.
  • FIG. 1 is a drawing of a video timeline for which a video fingerprint can be generated according to various embodiments of the disclosure.
  • FIG. 2 is a drawing of a portion of a video fingerprint corresponding to the video of FIG. 1 according to various embodiments of the disclosure.
  • FIG. 3A-3I are drawings illustrating matching of a video profile to the video fingerprint of FIG. 2 according to various embodiments of the disclosure.
  • FIGS. 4-5 are drawings of a computing environment in which a video fingerprinting application can be executed according to various embodiments of the disclosure.
  • FIGS. 6-7 are flowcharts illustrating one example of functionality implemented as portions of video fingerprinting application executed in a computing device of FIGS. 4-5 according to various embodiments of the present disclosure.
  • FIG. 8 is a schematic block diagram that provides one example illustration of a computing device employed in the computing environment of FIGS. 4-5 according to various embodiments of the present disclosure.
  • Embodiments of the disclosure are generally related to generating a fingerprint associated with a video as well as identifying a video by comparing a fingerprint associated with the video to a reference fingerprint.
  • Video fingerprinting is a general technique to identify and extract characteristic features of a video, enabling the video to be uniquely identified by its resulting fingerprint.
  • a video fingerprint generated according to embodiments of the disclosure is highly compressed compared to video itself, meaning it generally consumes much less data than the video to which it corresponds.
  • the video fingerprinting method disclosed herein is a symmetric process, meaning the process of identifying a reference fingerprint associated with a video is a similar process as that of generating the video fingerprint itself.
  • systems implementing the video fingerprinting process described herein can be employed to facilitate identifying an unknown video or video clip, retrieving metadata associated with a video from a database (e.g., title, genre, name of director, year filmed, names of actors, etc.), classifying or identifying a video for the purposes of digital rights management (DRM), tracking the distribution of unauthorized or illegal content, video search engines, content aware advertising, identifying a user's viewing choices and/or habits for sharing with others, identifying duplicate video clips in a large database, synchronized retrieval of closed caption data, and/or other applications as can be appreciated.
  • a database e.g., title, genre, name of director, year filmed, names of actors, etc.
  • DRM digital rights management
  • FIG. 1 illustrates a representation of a video to illustrate the theory of operation of the video fingerprinting technique according to an embodiment of the disclosure.
  • the depicted embodiment illustrates a portion of a video 101 represented over time.
  • the video fingerprinting technique disclosed herein involves detection of scene changes that occur in a video.
  • the scene changes (s 1 , s 2 , s 3 , s 4 , s 5 , s 6 , s 7 , etc.) occur at various points in time in the video.
  • Scene changes in a video source can be detected using various systems and methods known in the art. Accordingly, in order to generate a video fingerprint according to an embodiment of the disclosure, the various scene changes in a video can be detected as well as a time (e.g., relative to a starting point in the video) in the video at which each of the scene changes occur.
  • a video fingerprint associated with the video 101 is based upon at least two pieces of information, which include a time in the video associated with each of the scene changes as well as a time difference between successive scene changes.
  • FIG. 2 illustrates one representation of a video fingerprint 201 associated with a video according to an embodiment of the disclosure.
  • the video fingerprint 201 can represent a reference fingerprint of a video.
  • the video fingerprint 201 can be associated with a video identifier 203 that uniquely identifies a video with which the fingerprint 201 is associated. Any other identifying information associated with a video can also be associated with the identifier 203 and/or the fingerprint 201 that can be provided in various applications.
  • various metadata can also be associated with the video, which can be stored in the same or a different database that can be indexed by the video identifier 203 and/or the fingerprint 201 .
  • the video fingerprint 201 can include a representation of a table that comprises at least three types of data.
  • a scene start time of at least a subset of the scene changes in the video can be associated with at least two time differences between scene changes that are subsequent to the particular scene change.
  • the fingerprint 201 associates a scene change with a pairing of time intervals between the next two successive scene changes as shown.
  • the first entry in the table of the video fingerprint 201 associates a scene change start time s 1 with ⁇ t 1 and ⁇ t 2 , which represent a time difference between the scene change occurring at time s 1 in the video and the next two scene changes in the video, s 2 and s 3 .
  • the fingerprint 201 also associates a particular scene change with additional time difference or interval pairings that represent potential missed scene change detections.
  • the scene change start time s 1 is also associated with a time difference pairing of ⁇ t 1 and ⁇ t 2 + ⁇ t 3 , which represents a pairing of time intervals to the next two successive scene changes if detection of scene change s 3 is missed.
  • this pairing of time intervals represents the time interval to scene changes s 2 and s 4 , which accounts for the possibility that the scene change at s 2 is missed.
  • the scene change start time s 1 is also associated a time difference pairing of ⁇ t 1 + ⁇ t 2 and ⁇ t 3 , which represents a pairing of time intervals to next two successive scene changes if detection of scene change s 2 is missed.
  • the video fingerprint 201 table can include similar entries for successive scene changes.
  • a computing device can generate a table by detecting scene changes in the video and measuring a scene change start time as well as time intervals to the next two successive scene change for each detected scene change. The computing device can then attempt to match the generated table with a reference video fingerprint 201 , which can be stored in a database or other data store.
  • FIG. 3A illustrates an example.
  • the table shown in FIG. 3A illustrates an example of a table 301 representing a video profile that is generated in response to process a video in an attempt to identify a video fingerprint 201 with which the video matches.
  • FIG. 3A illustrates a case where detection of a scene change is not missed, nor are there any false positive scene change detections.
  • a computing device implementing a process whereby it attempts to match a video with a reference video fingerprint can compare the entries in the table generated by processing the video with various reference video fingerprints 201 until a match is found.
  • the reference video fingerprint 201 can be located by matching the time interval pairings in the table 301 .
  • the video fingerprinting process as well as the process of matching a video profile to a reference video fingerprint 201 can be conducted on any portion of the video 101 .
  • a video profile representing a clip of a reference video can be generated and compared to the reference video signature 101 to determine whether a match exists.
  • a video profile for a clip representing a few minutes from any portion of a reference video can be generated and matched according to the time at which scene changes occur and the intervals between them.
  • the first scene change in a video profile may not necessarily correspond to the first scene change in a reference video signature 201 , but instead may correspond to a scene change that occurs after many previous scene changes in the reference video.
  • the table 301 also includes the detected scene start times of the scene changes in the video being associated with at least two time differences between scene changes that are subsequent to the particular scene change.
  • the table 301 representing a video profile also associates a scene change with a pairing of time intervals between the next two successive scene changes as shown.
  • a match can be found with a reference video fingerprint 201 even in the event that the reference video fingerprint 201 may lack entries for certain scene changes (i.e., the reference video fingerprint 201 “missed” a scene change).
  • the video profile can also allow a match to be found against a reference video fingerprint 201 that includes false positive scene change entries.
  • the process of generating a video fingerprint 201 as well as generating a video profile that is used to match against a video fingerprint 201 are symmetric with respect to one another to account for potential errors in the reference video fingerprint 201 and/or the video profile. This is illustrated in further detail in FIGS. 3B-3I and discussed hereinbelow.
  • the scene start time in each entry of the table 301 can increase the confidence of a match.
  • Scene start times are measured relative to the time when video analysis is initiated.
  • a scene start time of a video under analysis may not represent an absolute scene start time, but a time in a video clip at which a scene change occurs relative to the beginning of a video clip, which can differ from the scene start time in a reference video as measured from the beginning of the reference video.
  • the scene start time values are not meant to be treated in an absolute sense.
  • Relative differences between the start times of corresponding interval pairings are meaningful. For example, a difference between s′ 1 in the table 301 and s 1 in the reference video signature 201 can be compared to a difference between s′ 2 in the table 301 and s 2 in the reference video signature 201 to determine if this difference is consistent. Therefore, a marked consistency in the relative scene start time differences between entries in the table 301 relative to the reference fingerprint 201 may increase a confidence score associated with a match. In the depicted example, a confidence score of a match between the example video fingerprint 201 shown in FIG. 2 and a video profile represented by the table 301 can be increased due to the similarity of time differences between each of the scene start times.
  • a confidence score can be generated that corresponds to a likelihood of a match between a table 301 and a reference video fingerprint 201 . It should be appreciated that scene change detection, whether tracked in terms of a frame number and/or running time in a video, may not result in an exact match between entries in a table 301 and a reference video fingerprint 201 . Accordingly, such a confidence score can be based at least upon an amount error or difference between entries in a table 301 and video fingerprint 201 . In some embodiments, a reference video fingerprint 201 that yields the smallest error and/or difference between entries in the table 301 and fingerprint 201 can be identified as a match.
  • FIGS. 3B and 3C illustrate a video profile corresponding to the video 101 shown in FIG. 1 .
  • a computing device generating a video profile corresponding to the video 101 has missed a scene change occurring at time s′ 3 in the video.
  • the reference video fingerprint 201 can still be matched with the video profile corresponding to the table 351 because the reference video fingerprint 201 contains entries that take into account potential missed scene change detections.
  • the table 351 represents a video profile generated in an attempt to identify a video fingerprint 201 with which the video matches.
  • the table 351 does not include an entry corresponding to a scene starting at time s′ 3 .
  • the reference video fingerprint 201 can still be matched with the table 351 shown in FIG. 3C despite the fact that the scene change was missed because of the entries taking into account potential missed detection of scene changes.
  • FIGS. 3D and 3E show the matching entries in the reference video fingerprint 201 and the table 351 corresponding to the video profile.
  • Entry 365 in the reference video fingerprint 201 constitutes a match with entry 375 in the table 351 .
  • entry 369 in the reference video fingerprint 201 constitutes a match with entry 379 in the table 351 , and so on. Accordingly, despite the fact that detection of scene change s 3 was missed, the profile corresponding to the table 351 can still be matched with the reference video fingerprint 201 .
  • FIGS. 3F and 3G illustrate an alternative example of a video profile corresponding to the video 101 shown in FIG. 1 .
  • a computing device generating a video profile corresponding to the video 101 has detected a false positive scene change.
  • a scene change has been detected at a time within the video where the reference video fingerprint does not reflect a corresponding scene change.
  • this false positive scene change is denoted by f 1 .
  • f 1 this false positive scene change.
  • the table 381 corresponding to the video profile associated with the video 101 includes an additional series of entries corresponding to the false positive scene change f 1 that are not included within the reference video fingerprint 201 .
  • the video profile may correctly reflect the scene changes while the reference video fingerprint 201 contains a missed scene change, which would result in a similar situation.
  • the video profile corresponding to the table 381 can still be matched to the corresponding reference video fingerprint 201 .
  • FIGS. 3H and 3I show the matching entries in the reference video fingerprint 201 and table 381 corresponding to the video profile.
  • Entry 383 in the reference video fingerprint 201 constitutes a match with entry 391 in the table 381 .
  • entry 385 in the reference video fingerprint 201 constitutes a match with entry 393 in the table 381 , and so on. Accordingly, despite the fact that a false positive scene change f 1 was detected, the profile corresponding to the table 381 can still be matched with the reference video fingerprint 201 .
  • a video profile that may include various combinations of false positives and/or missed scene change detections can be matched with a reference video fingerprint 201 by employing the process described herein.
  • the error robustness can be improved by extending the video fingerprint to associate more than two time intervals and the associated permutations of additional intervals to account for missed scene change detections.
  • the video fingerprint can be extended to associate a scene change with the next three, four, or any number of subsequent scene changes.
  • each scene change in the video fingerprint would be associated with the time interval to the next X scene changes, where X is any positive integer.
  • the scene change would also be associated with the time intervals associated with the various permutations of potential missed scene change detections consistent with the example described above in FIG. 2 .
  • embodiments employing the video fingerprint and matching processes consistent with the above can result in computationally efficient fingerprint generation and matching with compact video fingerprints for efficient transmission and storage. Additionally, systems and methods employing such a scheme can be capable of identifying a short segment or clip of a reference video. By relying on detection of scene changes as well as a time interval between subsequent scene changes, the process is also noise resistant and can account for encoding differences between a reference video and video under analysis.
  • Encoding differences can result due to transcoding, video being captured via a video camera (e.g., mobile device, smartphone, tablet computing system, laptop computer), misaligned framing, camera shake, and/or variations in frame rate between a reference video and video under analysis,
  • a video camera e.g., mobile device, smartphone, tablet computing system, laptop computer
  • misaligned framing camera shake
  • variations in frame rate between a reference video and video under analysis
  • the process is also resistant to differences in picture quality between a reference video and video under analysis.
  • picture quality characteristics can include, but are not limited to, sharpness, contrast, brightness, hue, saturation, scaling, etc.
  • FIG. 4 illustrates an embodiment of at least one computing device 401 in which an embodiment of the disclosure can be implemented.
  • the depicted configuration of a computing device 401 can be one in which a video fingerprint corresponding to a video is generated according to the methodology described above.
  • the computing device 401 may comprise, for example, a server computer or any other system providing computing capability.
  • a plurality of computing devices 401 may be employed that are arranged, for example, in one or more server banks or computer banks or other arrangements.
  • a plurality of computing devices 401 together may comprise a cloud computing resource, a grid computing resource, and/or any other distributed computing arrangement.
  • Such computing devices 401 may be located in a single installation or may be distributed among many different geographical locations.
  • the computing device 401 is referred to herein in the singular. Even though the computing device is referred to in the singular, it is understood that a plurality of computing devices 401 may be employed in the various arrangements as described above.
  • the computing device 401 may comprise, for example, a processor-based system such as a computer system.
  • a computer system may be embodied in the form of a desktop computer, a laptop computer, a personal digital assistant, a cellular telephone, set-top box, music players, mobile computing device, tablet computer systems, game consoles, or other devices with like capability.
  • the data stored in the data store 402 includes, for example, video data 403 associated with various videos for which video fingerprints 405 as well as metadata 407 can be associated, as well as potentially other data about videos indexed by a system according to an embodiment of the disclosure.
  • An entry corresponding to a particular video can be indexed by a video identifier 404 that uniquely identifies the video.
  • the data store 402 can represent a relational or non-relational database or other data storage system that can also be executed in a dedicated computing system that is accessible to the computing device 401 via a network.
  • the computing device 401 can execute a video fingerprinting application 411 , which can receive a video 413 as an input and generate a video fingerprint 415 as described above.
  • the video fingerprinting application 411 can generate a reference video fingerprint 405 associated with the video 413 .
  • the video 413 can be indexed by its video fingerprint 405 and/or a video identifier 404 based upon a video fingerprint 415 generated by the video fingerprinting application 411 that is based upon detected scene changes within the video as well as time intervals between the various scene changes.
  • the video fingerprinting application 411 can contain logic that facilitates identification of scene changes within a video 413 .
  • the video fingerprinting application 411 can rely on scene change logic provided by an application programming interface that accesses external software and/or hardware logic that facilitates scene change detection.
  • FIG. 5 an alternative depiction of a computing device 401 executing the video fingerprinting application 411 is shown.
  • the video fingerprinting application 411 can receive a video 521 and generate a video profile 533 as described above in reference to FIGS. 3A-3B .
  • the video fingerprinting application 411 can identify scene changes as well as intervals between scene changes in the video 521 to generate the video profile 533 .
  • the video fingerprinting application 411 can determine whether a video corresponding to video data 403 in the data store 402 matches the video profile 533 and return a video identifier 540 for the corresponding video.
  • a video profile 533 can be generated by a client device that is viewing and/or capturing a video 521 , with at least a portion of the video profile 533 generated by a client device submitting a request to the video fingerprinting application 411 to find a matching video.
  • a client device such as a mobile device that is capturing a video for which it desires a matching video to be located, can provide a partial video profile that includes a list of times in the video 521 at which scene changes are detected.
  • the video fingerprinting application 411 can determine time intervals between successive scene changes corresponding to each identified scene change as described with reference to FIGS. 3A-3B .
  • the video fingerprinting application 411 can then identify a matching video in the data store by identifying a video fingerprint 405 that matches the video profile 533 with the highest degree of confidence.
  • FIG. 6 shown is a flowchart that provides one example of the operation of a portion of the video fingerprinting application 411 to generate a video fingerprint according to various embodiments. It is understood that the flowchart of FIG. 6 provides merely an example of the many different types of functional arrangements that may be employed to implement the operation of the portion of the video fingerprinting application 411 as described herein. As an alternative, the flowchart of FIG. 6 may be viewed as depicting an example of steps of a method implemented in the computing device 401 according to one or more embodiments.
  • a plurality of scene changes are detected within the video.
  • scene changes can be detected using a scene change detection API that provides access to hardware and/or software logic facilitating scene change detection.
  • the time at which scene changes occur in the video are detected.
  • the video fingerprinting application 411 can detect a time interval between adjacent scene changes in the video.
  • the video fingerprinting application 411 can generate a video fingerprint based upon the time at which scene changes occur and a time interval between adjacent scene changes where the fingerprint also takes into account the potential for missed or false positive detection of scene changes as described above.
  • FIG. 7 shown is a flowchart that provides one example of the operation of a portion of the video fingerprinting application 411 to identify a reference video fingerprint with which a video profile is matched in a database or other repository of video fingerprint data according to various embodiments. It is understood that the flowchart of FIG. 7 provides merely an example of the many different types of functional arrangements that may be employed to implement the operation of the portion of the video fingerprinting application 411 as described herein. As an alternative, the flowchart of FIG. 7 may be viewed as depicting an example of steps of a method implemented in the computing device 401 according to one or more embodiments.
  • first, in box 701 can detect scene changes in a video as well as identify a time at which scene changes occur in the video in box 703 .
  • time intervals between adjacent scene changes are determined.
  • a video profile that describes the time at which scene changes occur as well as the time interval between subsequent scene changes is generated.
  • the video fingerprinting application 411 identifies whether a reference video fingerprint matches the generated video profile. As noted above, some or all the functionality described pertaining to identification of a reference video fingerprint corresponding to a video may be performed in a client.
  • a client device may record a video source with an integrated video camera and submit the video and/or scene change data from the video to a computing device executing the video fingerprinting application 411 , which can determine if the video matches a reference video fingerprint.
  • the video fingerprinting application 411 can scan a corpus of videos and analyze scene change properties of the videos to identify potential matching reference video fingerprints in a database. It should be appreciated that many other variations applying the process of generating and matching a video fingerprint can be employed consistent with the present disclosure.
  • the computing device 401 may include one or more processor circuits having a processor 803 and a memory 806 , both of which are coupled to a local interface 809 .
  • the local interface 809 may comprise, for example, a data bus with an accompanying control/address bus as can be appreciated.
  • Stored on the memory 806 and executable by the processor 803 are various components such as an operating system 813 , video fingerprinting application 411 , and other applications or data. In addition, it is understood that many other components may be stored in the memory 806 and executable by the processor(s) 803 . Also, such components may reside in a memory that is external from the computing device 401 as can be appreciated.
  • executable refers to a program file that is in a form that can ultimately be run by the processor 803 .
  • Examples of executable programs may be, for example, a compiled program that can be translated into machine code in a format that can be loaded into a random access portion of the memory 806 and run by the processor 803 , or source code that may be expressed in proper format such as object code that is capable of being loaded into a random access portion of the memory 806 and executed by the processor 803 .
  • An executable program may be stored in any portion or component of the memory 806 including, for example, random access memory, read-only memory, a hard drive, compact disk (CD), floppy disk, or other memory components.
  • the memory 806 is defined herein as both volatile and nonvolatile memory and data storage components. Volatile components are those that do not retain data values upon loss of power. Nonvolatile components are those that retain data upon a loss of power.
  • the memory 806 may comprise, for example, random access memory (RAM), read-only memory (ROM), hard disk drives, floppy disks accessed via an associated floppy disk drive, compact discs accessed via a compact disc drive, magnetic tapes accessed via an appropriate tape drive, and/or other memory components, or a combination of any two or more of these memory components.
  • the RAM may comprise, for example, static random access memory (SRAM), dynamic random access memory (DRAM), or magnetic random access memory (MRAM) and other such devices.
  • the ROM may comprise, for example, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other like memory device.
  • the processor 803 may represent multiple processors and the memory 806 may represent multiple memories that operate in parallel.
  • the local interface 809 may be an appropriate network that facilitates communication between any two of the multiple processors, between any processor and any one of the memories, or between any two of the memories, etc.
  • the processor 803 may be of electrical, optical, or of some other construction as can be appreciated by those with ordinary skill in the art.
  • the operating system 813 is executed to control the allocation and usage of hardware resources such as the memory and processing time in the computing device 401 .
  • the server operating system 813 serves as the foundation on which applications depend as is generally known by those with ordinary skill in the art.
  • the functionality of various components are described above with respect to FIGS. 1-7 , such as, for example, the video fingerprinting application 411 , as being embodied in software or code executed by general purpose hardware as discussed above, as an alternative the same may also be embodied in dedicated hardware or a combination of software/general purpose hardware and dedicated hardware. If embodied in dedicated hardware, the functionality of these components can be implemented as a circuit or state machine that employs any one of or a combination of a number of technologies. These technologies may include, but are not limited to, discrete logic circuits having logic gates for implementing various logic functions upon an application of one or more data signals, application specific integrated circuits having appropriate logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), or other components, etc. Such technologies are generally well known by those skilled in the art and, consequently, are not described in detail herein.
  • each block may represent a module, segment, or portion of code that comprises program instructions to implement the specified logical function(s).
  • the program instructions may be embodied in the form of source code that comprises human-readable statements written in a programming language or machine code that comprises numerical instructions recognizable by a suitable execution system such as a processor in a computer system or other system.
  • the machine code may be converted from the source code, etc.
  • each block may represent a circuit or a number of interconnected circuits to implement the specified logical function(s).
  • the functionality of the disclosed systems can be embodied in any computer-readable medium for use by or in connection with an instruction execution system such as, for example, a processor in a computer system or other system.
  • the functionality may comprise, for example, statements including instructions and declarations that can be fetched from the computer-readable medium and executed by the instruction execution system.
  • a “computer-readable medium” can be any medium that can contain, store, or maintain the network page for use by or in connection with the instruction execution system.
  • the computer readable medium can comprise any one of many physical media such as, for example, electronic, magnetic, optical, or semiconductor media. More specific examples of a suitable computer-readable medium would include, but are not limited to, magnetic tapes, magnetic floppy diskettes, magnetic hard drives, or compact discs. Also, the computer-readable medium may be a random access memory (RAM) including, for example, static random access memory (SRAM) and dynamic random access memory (DRAM), or magnetic random access memory (MRAM). In addition, the computer-readable medium may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other type of memory device.
  • RAM random access memory
  • PROM programmable read-only memory
  • EPROM erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Collating Specific Patterns (AREA)
  • Image Processing (AREA)
  • Image Input (AREA)
US13/334,201 2011-12-22 2011-12-22 System and method for fingerprinting video Active 2032-03-14 US8538239B2 (en)

Priority Applications (6)

Application Number Priority Date Filing Date Title
US13/334,201 US8538239B2 (en) 2011-12-22 2011-12-22 System and method for fingerprinting video
EP12005902.7A EP2608107A3 (en) 2011-12-22 2012-08-16 System and method for fingerprinting video
TW101132784A TWI551134B (zh) 2011-12-22 2012-09-07 在至少一個計算設備中執行視頻指紋生成及識別的方法及系統
KR1020120105197A KR20130079123A (ko) 2011-12-22 2012-09-21 비디오 핑거프린팅을 위한 시스템 및 방법
CN201210371363.7A CN103198293B (zh) 2011-12-22 2012-09-28 用于指纹识别视频的系统和方法
US13/968,616 US9185338B2 (en) 2011-12-22 2013-08-16 System and method for fingerprinting video

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US13/334,201 US8538239B2 (en) 2011-12-22 2011-12-22 System and method for fingerprinting video

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13/968,616 Continuation US9185338B2 (en) 2011-12-22 2013-08-16 System and method for fingerprinting video

Publications (2)

Publication Number Publication Date
US20130163957A1 US20130163957A1 (en) 2013-06-27
US8538239B2 true US8538239B2 (en) 2013-09-17

Family

ID=46754846

Family Applications (2)

Application Number Title Priority Date Filing Date
US13/334,201 Active 2032-03-14 US8538239B2 (en) 2011-12-22 2011-12-22 System and method for fingerprinting video
US13/968,616 Active 2032-02-14 US9185338B2 (en) 2011-12-22 2013-08-16 System and method for fingerprinting video

Family Applications After (1)

Application Number Title Priority Date Filing Date
US13/968,616 Active 2032-02-14 US9185338B2 (en) 2011-12-22 2013-08-16 System and method for fingerprinting video

Country Status (5)

Country Link
US (2) US8538239B2 (zh)
EP (1) EP2608107A3 (zh)
KR (1) KR20130079123A (zh)
CN (1) CN103198293B (zh)
TW (1) TWI551134B (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130330057A1 (en) * 2011-12-22 2013-12-12 Broadcom Corporation System and Method for Fingerprinting Video
US10419816B2 (en) 2014-06-27 2019-09-17 Tencent Technology (Shenzhen) Company Limited Video-based check-in method, terminal, server and system
US11961299B2 (en) 2018-08-09 2024-04-16 Alibaba Group Holding Limited Method and apparatus for generating video fingerprint

Families Citing this family (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8918804B2 (en) 2012-02-07 2014-12-23 Turner Broadcasting System, Inc. Method and system for a reward program based on automatic content recognition
US9167278B2 (en) 2012-12-28 2015-10-20 Turner Broadcasting System, Inc. Method and system for automatic content recognition (ACR) based broadcast synchronization
US9495451B2 (en) 2013-01-07 2016-11-15 Gracenote, Inc. Identifying video content via fingerprint matching
US9323840B2 (en) * 2013-01-07 2016-04-26 Gracenote, Inc. Video fingerprinting
US9930375B2 (en) * 2014-06-16 2018-03-27 Nexidia Inc. Media asset management
US9531488B2 (en) 2015-04-01 2016-12-27 Tribune Broadcasting Company, Llc Using single-channel/multi-channel transitions to output an alert indicating a functional state of a back-up audio-broadcast system
US9621935B2 (en) 2015-04-01 2017-04-11 Tribune Broadcasting Company, Llc Using bitrate data to output an alert indicating a functional state of back-up media-broadcast system
US9420348B1 (en) 2015-04-01 2016-08-16 Tribune Broadcasting Company, Llc Using aspect-ratio transitions to output an alert indicating a functional state of a back up video-broadcast system
US9420277B1 (en) * 2015-04-01 2016-08-16 Tribune Broadcasting Company, Llc Using scene-change transitions to output an alert indicating a functional state of a back-up video-broadcast system
US9674475B2 (en) 2015-04-01 2017-06-06 Tribune Broadcasting Company, Llc Using closed-captioning data to output an alert indicating a functional state of a back-up video-broadcast system
US9264744B1 (en) 2015-04-01 2016-02-16 Tribune Broadcasting Company, Llc Using black-frame/non-black-frame transitions to output an alert indicating a functional state of a back-up video-broadcast system
US9582244B2 (en) 2015-04-01 2017-02-28 Tribune Broadcasting Company, Llc Using mute/non-mute transitions to output an alert indicating a functional state of a back-up audio-broadcast system
US9807453B2 (en) * 2015-12-30 2017-10-31 TCL Research America Inc. Mobile search-ready smart display technology utilizing optimized content fingerprint coding and delivery
WO2017133213A1 (zh) * 2016-02-01 2017-08-10 北京小米移动软件有限公司 指纹识别方法和装置
US10701438B2 (en) 2016-12-31 2020-06-30 Turner Broadcasting System, Inc. Automatic content recognition and verification in a broadcast chain
GB2562515A (en) * 2017-05-17 2018-11-21 Snell Advanced Media Ltd Generation of audio or video hash
CN107704570A (zh) * 2017-09-30 2018-02-16 韦彩霞 一种高效的多媒体教学管理系统
CN107862306A (zh) * 2017-12-07 2018-03-30 潘淑斐 指纹识别多功能播放器
US10713495B2 (en) 2018-03-13 2020-07-14 Adobe Inc. Video signatures based on image feature extraction
KR102546026B1 (ko) 2018-05-21 2023-06-22 삼성전자주식회사 전자 장치 및 그의 컨텐츠 인식 정보 획득
US11006022B2 (en) * 2018-05-23 2021-05-11 Novatek Microelectronics Corp. Video system and related method
KR102599951B1 (ko) 2018-06-25 2023-11-09 삼성전자주식회사 전자 장치 및 그의 제어방법
CN111259708A (zh) * 2018-12-03 2020-06-09 敦泰电子有限公司 指纹识别方法、存储介质、指纹识别系统及智能装置
CN109361923B (zh) * 2018-12-04 2022-05-31 深圳市梦网视讯有限公司 一种基于运动分析的滑动时间窗场景切换检测方法和系统
KR20200080387A (ko) 2018-12-18 2020-07-07 삼성전자주식회사 디스플레이 장치 및 그 제어 방법
CN112291634B (zh) * 2019-07-25 2022-11-29 腾讯科技（深圳）有限公司 视频处理方法及装置
CN111898461B (zh) * 2020-07-08 2022-08-30 贵州大学 一种时序行为片段生成方法
CN112866800A (zh) * 2020-12-31 2021-05-28 四川金熊猫新媒体有限公司 视频内容相似性检测方法、装置、设备及存储介质
CN112839257B (zh) * 2020-12-31 2023-05-09 四川金熊猫新媒体有限公司 视频内容检测方法、装置、服务器及存储介质

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090167942A1 (en) * 2006-06-13 2009-07-02 Koninklijke Philips Electronics N.V. Fingerprint, apparatus, method for identifying and synchronizing video
US20090328237A1 (en) * 2008-06-30 2009-12-31 Rodriguez Arturo A Matching of Unknown Video Content To Protected Video Content

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2627267C (en) * 2004-11-30 2013-10-15 The University Court Of The University Of St Andrews System, method & computer program product for video fingerprinting
GB0917417D0 (en) * 2009-10-05 2009-11-18 Mitsubishi Elec R&D Ct Europe Multimedia signature coding and decoding
US8538239B2 (en) * 2011-12-22 2013-09-17 Broadcom Corporation System and method for fingerprinting video

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090167942A1 (en) * 2006-06-13 2009-07-02 Koninklijke Philips Electronics N.V. Fingerprint, apparatus, method for identifying and synchronizing video
US20090328237A1 (en) * 2008-06-30 2009-12-31 Rodriguez Arturo A Matching of Unknown Video Content To Protected Video Content

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130330057A1 (en) * 2011-12-22 2013-12-12 Broadcom Corporation System and Method for Fingerprinting Video
US9185338B2 (en) * 2011-12-22 2015-11-10 Broadcom Corporation System and method for fingerprinting video
US10419816B2 (en) 2014-06-27 2019-09-17 Tencent Technology (Shenzhen) Company Limited Video-based check-in method, terminal, server and system
US11961299B2 (en) 2018-08-09 2024-04-16 Alibaba Group Holding Limited Method and apparatus for generating video fingerprint

Also Published As

Publication number Publication date
TW201328338A (zh) 2013-07-01
CN103198293A (zh) 2013-07-10
EP2608107A2 (en) 2013-06-26
TWI551134B (zh) 2016-09-21
KR20130079123A (ko) 2013-07-10
CN103198293B (zh) 2018-06-08
US20130163957A1 (en) 2013-06-27
US20130330057A1 (en) 2013-12-12
EP2608107A3 (en) 2013-09-25
US9185338B2 (en) 2015-11-10

Similar Documents

Publication Publication Date Title
US9185338B2 (en) System and method for fingerprinting video
EP3477506B1 (en) Video detection method, server and storage medium
US8347408B2 (en) Matching of unknown video content to protected video content
US8259177B2 (en) Video fingerprint systems and methods
Lu Video fingerprinting for copy identification: from research to industry applications
JP5980311B2 (ja) ビデオ・シグネチャ
US8856051B1 (en) Augmenting metadata of digital objects
US20170185675A1 (en) Fingerprinting and matching of content of a multi-media file
US20090327334A1 (en) Generating Measures of Video Sequences to Detect Unauthorized Use
CA2918592C (en) Generating and providing an authorization indication in relation to a media content item
US11526586B2 (en) Copyright detection in videos based on channel context
Jeysudha et al. Real Time Video Copy Detection using Hadoop
Breitinger et al. DFRWS EU 10-year review and future directions in Digital Forensic Research
US10162488B1 (en) Browser-based media scan
JP2011248671A (ja) 多数の参照用映像の中から検索キー用映像を用いて検索する映像検索装置、プログラム及び方法
US11714847B2 (en) Methods and apparatus to detect unconfined view media
Roopalakshmi A novel framework for CBCD using integrated color and acoustic features
Liu et al. A novel robust video fingerprinting-watermarking hybrid scheme based on visual secret sharing
US11966500B2 (en) Systems and methods for isolating private information in streamed data
US10771568B2 (en) System for intercepting and reconstructing session data for web incidents
Ortega Hiding in plain sight? The impact of face recognition services on privacy
Li et al. Forensic authentication examination of webcam videos
Pedro et al. Web‐Based Multimedia Information Extraction Based on Social Redundancy

Legal Events

Date Code Title Description
AS Assignment

Owner name: BROADCOM CORPORATION, CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:IKIZYAN, IKE;KELLERMAN, MARCUS;REEL/FRAME:027597/0814

Effective date: 20111221

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: BANK OF AMERICA, N.A., AS COLLATERAL AGENT, NORTH CAROLINA

Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:BROADCOM CORPORATION;REEL/FRAME:037806/0001

Effective date: 20160201

Owner name: BANK OF AMERICA, N.A., AS COLLATERAL AGENT, NORTH

Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:BROADCOM CORPORATION;REEL/FRAME:037806/0001

Effective date: 20160201

AS Assignment

Owner name: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD., SINGAPORE

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:BROADCOM CORPORATION;REEL/FRAME:041706/0001

Effective date: 20170120

Owner name: AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:BROADCOM CORPORATION;REEL/FRAME:041706/0001

Effective date: 20170120

AS Assignment

Owner name: BROADCOM CORPORATION, CALIFORNIA

Free format text: TERMINATION AND RELEASE OF SECURITY INTEREST IN PATENTS;ASSIGNOR:BANK OF AMERICA, N.A., AS COLLATERAL AGENT;REEL/FRAME:041712/0001

Effective date: 20170119

FPAY Fee payment

Year of fee payment: 4

AS Assignment

Owner name: AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITE

Free format text: MERGER;ASSIGNOR:AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.;REEL/FRAME:047230/0910

Effective date: 20180509

AS Assignment

Owner name: AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITE

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE EFFECTIVE DATE OF THE MERGER PREVIOUSLY RECORDED AT REEL: 047230 FRAME: 0910. ASSIGNOR(S) HEREBY CONFIRMS THE MERGER;ASSIGNOR:AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.;REEL/FRAME:047351/0384

Effective date: 20180905

AS Assignment

Owner name: AVAGO TECHNOLOGIES INTERNATIONAL SALES PTE. LIMITE

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE ERROR IN RECORDING THE MERGER IN THE INCORRECT US PATENT NO. 8,876,094 PREVIOUSLY RECORDED ON REEL 047351 FRAME 0384. ASSIGNOR(S) HEREBY CONFIRMS THE MERGER;ASSIGNOR:AVAGO TECHNOLOGIES GENERAL IP (SINGAPORE) PTE. LTD.;REEL/FRAME:049248/0558

Effective date: 20180905

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 8